Rate this Page
★★★★★

Hardswish#

classtorch.nn.modules.activation.Hardswish(inplace=False)[source]#

Applies the Hardswish function, element-wise.

Method described in the paper:Searching for MobileNetV3.

Hardswish is defined as:

Hardswish(x)={0if x≤−3,xif x≥+3,x⋅(x+3)/6otherwise\text{Hardswish}(x) = \begin{cases} 0 & \text{if~} x \le -3, \\ x & \text{if~} x \ge +3, \\ x \cdot (x + 3) /6 & \text{otherwise}\end{cases}
Parameters

inplace (bool) – can optionally do the operation in-place. Default:False

Shape:

  • Input:(∗)(*), where∗* means any number of dimensions.

  • Output:(∗)(*), same shape as the input.

../_images/Hardswish.png

Examples:

>>>m=nn.Hardswish()>>>input=torch.randn(2)>>>output=m(input)
forward(input)[source]#

Runs the forward pass.

Return type

Tensor